CollectSEA

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. Since there is no output schema, the description's enumeration of what comes back (incidents, failure patterns, safeguards) is genuinely additive behavioral information, though it gives no detail on result format or behavior when nothing matches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, and the purpose is front-loaded before the usage triggers. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, two-parameter analysis tool with no output schema, the description covers purpose, inputs, triggers, and the shape of the return value. It leaves minor gaps around result format and empty-result behavior, but nothing essential to invoking it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: the required 'proposal' parameter is well documented in the schema (2-5 sentences covering what the system does, changes, reads, and calls), while 'max_results' is only bounded by min/max/default with no prose. The description's 'proposed feature, system or AI-agent workflow' loosely echoes the proposal scope but adds no syntax or format guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action (profile a proposed feature/system/workflow) and a specific deliverable (documented incidents from similar systems, their failure patterns, and safeguards). The word 'proposed' implicitly contrasts with the sibling analyze_existing_app, but no sibling is named explicitly, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use before writing code for anything that moves money, deletes data, changes permissions, runs code, or acts on external content' gives concrete, actionable trigger conditions for when to reach for this tool. It does not, however, state when NOT to use it or point to alternatives such as analyze_existing_app for already-built systems.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: static analysis only, no code execution, no scanning of the live app, and a one-commit snapshot import for public repos. It stops short of describing result format or limits on the returned precedents.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with purpose, then intake paths, then the important no-execution caveat, then outputs. Dense but every sentence carries information; the middle sentence is long but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly closes the loop by naming what comes back (source context, behavior signals, historical precedents, safeguards to verify). Combined with the privacy/limit notes in the schema, an agent has enough to call this correctly; only result volume/shape is unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, and the description complements it by explaining the anyOf intake alternatives: import a public GitHub repo URL, or inspect a private repo locally and submit text via files/proposal. It clarifies the public-only nature of repository_url and the private-repo workaround, though max_results is never acknowledged.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Analyze an existing app') and enumerates the evidence types it consumes (observed behavior, README, architecture notes, config, source snippets), which implicitly separates it from analyze_design. It does not explicitly name any sibling, so an agent still has to infer the boundary with list_failure_patterns or analyze_design.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains the two intake paths (public GitHub URL import vs. submitting text from a locally inspected private repo) and states the hard constraint that code is never executed and the running app is not scanned. However, it gives no explicit when-to-use / when-not-to-use guidance relative to the failure-precedent and incident siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description usefully adds the shape of the return payload (the record's constituent fields), which matters here because there is no output schema; it does not address missing-record or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, no filler, and the key operation and identifier example are front-loaded. Every clause earns its place by describing what the record contains.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read tool with no output schema, the description carries the return-value burden and does so by enumerating the record's fields. Only the failure/not-found case is unaddressed, which is a minor omission for a retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single parameter is bare, so the description must compensate — and it does, supplying a concrete ID example ('SEA-POST-005') that conveys the expected identifier format. It stops short of stating whether the ID is case-sensitive or the exact matching rules.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb+resource: 'Full record for one incident by ID' plus an enumeration of the returned content (what happened, source, failure pattern, safeguards, review status). It reads as distinct from search_incidents by framing itself as a single-record lookup, but it never names the sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the 'by ID' framing signals this is the retrieval path once an ID is known, versus search_incidents for discovery. There is no explicit statement of when to prefer this tool, nor any exclusion or prerequisite (e.g. what happens if the ID is unknown).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description still adds real behavioral context by disclosing the shape of the payload — ready-to-save rule files in named formats, each rule citing its source incidents — which is more than the annotations provide. It omits whether this triggers analysis or reads cached results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the default format stated first and the alternatives parenthesized; no filler, and the novel detail (incident citations) lands at the end where it is easiest to skim.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotation coverage of return values, the description does explain what comes back (rule files plus supporting incident citations), which is enough for a simple read-only tool. It is thin only on the effect of 'mode' and on what the agent should pass as 'proposal'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, and it only partially does. It clarifies the 'format' enum by naming the concrete outputs (AGENTS.md default, CLAUDE.md, Cursor rule, Copilot instructions), but says nothing about the 'mode' enum (design vs existing_app) or what 'proposal' should contain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Return ready-to-save rules') and names the concrete artifacts (AGENTS.md, CLAUDE.md, Cursor rule, Copilot instructions), so an agent knows exactly what it gets back. It does not, however, distinguish itself from siblings like analyze_design or analyze_existing_app, which appear to operate on the same inputs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'for a proposed design' implies the context of use, but there is no explicit statement of when to call this versus analyze_design/analyze_existing_app, nor any note that the 'mode' parameter switches between design and existing_app scenarios. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly=true, idempotent=true, destructive=false and openWorld=false, so safety is covered. The description goes beyond them by disclosing the payload's content shape and cardinality (14 patterns, each with triggers, warning signs, principles), which is genuinely useful given there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded clause with zero padding; the count and the returned facets come first. It is a verbless fragment, which costs it a little as a standalone statement but wastes no words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the necessary work of naming the fields each pattern contains and how many there are. What remains unstated is how this catalogue relates to the analysis tools (analyze_design, get_safeguards), which would help an agent sequence its calls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; schema coverage is moot at 0 params. Baseline 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource — the 14 recurring failure patterns — and enumerates the facets each entry carries (triggers, warning signs, engineering principles). It is clearly distinguishable in subject matter from siblings like get_incident or analyze_design, but it does not explicitly contrast itself with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use statement or named alternative. For a zero-parameter reference catalogue the usage is largely self-evident (consult the pattern list before analyzing a design), so guidance is only implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful behavior: what a result contains (titles, summaries, evidence labels, URLs), which annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, zero filler, with the search scope front-loaded and the return shape following. Nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly steps in to describe return fields, and annotations carry the safety profile. The only gap is the undocumented include_advisories parameter and lack of routing guidance against siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% — query, cursor and max_results are documented in the schema, but include_advisories has no description anywhere. The description's mention of advisories hints at that flag but does not explain its effect, so it only marginally compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (keyword search) and resource (documented incidents and security advisories) and even enumerates the searchable facets (company, technology, CVE, failure mode). It is easily distinguished from get_incident or list_failure_patterns by its keyword-search framing, though it never names those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to search versus when to fetch a specific incident via get_incident, nor any prerequisites or exclusions. The usage context is only implied by the word 'search'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.